CN110378260A - Real-time disconnecting link status tracking method and system based on KCF - Google Patents
Real-time disconnecting link status tracking method and system based on KCF Download PDFInfo
- Publication number
- CN110378260A CN110378260A CN201910605666.2A CN201910605666A CN110378260A CN 110378260 A CN110378260 A CN 110378260A CN 201910605666 A CN201910605666 A CN 201910605666A CN 110378260 A CN110378260 A CN 110378260A
- Authority
- CN
- China
- Prior art keywords
- disconnecting link
- image
- frame image
- real
- kcf
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 23
- 239000000284 extract Substances 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 14
- 210000004027 cell Anatomy 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 5
- 102000008297 Nuclear Matrix-Associated Proteins Human genes 0.000 description 2
- 108010035916 Nuclear Matrix-Associated Proteins Proteins 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 210000000299 nuclear matrix Anatomy 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 125000006850 spacer group Chemical group 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Abstract
The invention discloses the real-time disconnecting link status tracking methods based on KCF, comprising the following steps: step 1, current frame image, which initializes, determines target area；Step 2 extracts HOG feature to the current frame image；The window of step 3, the mobile target area generates sample image；Step 4 utilizes sample image training ridge regression classifier；Step 5 predicts next frame image using the ridge regression classifier, generates fresh target region, obtain the disconnecting link position of current frame image, repeat step 2 to step 5；Step 6 judges the disconnecting link position of consecutive frame image, realizes status tracking.The present invention also proposes the real-time disconnecting link status tracking system based on KCF.The present invention is based on KCF algorithms to carry out target locating to disconnecting link monitor video, and the state for obtaining disconnecting link in video in real time greatly reduces operand, improves arithmetic speed, algorithm is made to meet requirement of real-time.
Description
Technical field
The present invention relates to technical field of power transmission, more particularly to the real-time disconnecting link status tracking method based on KCF and are
System.
Background technique
In the power system, the connecting and disconnecting of high-current circuit are controlled by disconnecting link, and disconnecting link is electric power transmission pick-up
Main on-off controller part in route, the identification to its state are an important process in line data-logging.
Conventional method is to send operator's site observation, due to factors such as the distance of substation, distribution and quantity,
The method is time-consuming and laborious, inefficiency, and under specific circumstances, the static indication system inside high-tension switch cabinet can not be straight
Sight, the virtual condition for correctly showing disconnecting link, this just needs measure that can carry out Direct Recognition to disconnecting link state, be avoided middle spacer step
Suddenly it goes wrong and causes state recognition mistake.
Some researchers on common disconnecting link by installing perception unit, the intelligent recognition of Lai Shixian disconnecting link state additional.It is logical
It is more accurate to the identification of state to cross perception unit, but this loading pattern also results in installation complexity and equipment O&M cost
It is promoted, is not suitable with application on a large scale.
Summary of the invention
For above-mentioned prior art Shortcomings, the present invention provides the real-time disconnecting link status tracking method based on KCF and is
System carries out mesh to disconnecting link monitor video based on KCF algorithm (Kernel Correlation Filter, core correlation filtering)
Mark locating and tracking, obtain the state of disconnecting link in video in real time, convenient and efficient, greatly reduce manpower during line data-logging at
This.
The technical solution adopted by the present invention are as follows:
Real-time disconnecting link status tracking method based on KCF, comprising the following steps:
Step 1 initializes current frame image and determines target area；
Step 2 extracts HOG feature to the current frame image；
The window of step 3, the mobile target area generates sample image；
Step 4 utilizes sample image training ridge regression classifier；
Step 5 predicts next frame image using the ridge regression classifier, generates fresh target region, obtain current frame image
Disconnecting link position repeats step 2 to step 5；
Step 6 judges the disconnecting link position of consecutive frame image, realizes status tracking.
As further technical solution of the invention are as follows: described initialize to current frame image determines target area；Tool
Body are as follows:
Current frame image is initialized using the graphic feature of disconnecting link and determines target area.
As further technical solution of the invention are as follows: it is described that HOG feature is extracted to the current frame image, it is specific to wrap
It includes:
Gray processing processing is carried out to image and forms gray level image；
The gray level image is corrected to form correction image；
The horizontal direction of each pixel and the gradient of vertical direction in the correction image are calculated, the ladder of each location of pixels is obtained
Spend amplitude and direction；
The correction image is divided into cell factory, gradient direction is mapped in a certain range, by the gradient magnitude of pixel
It is projected as weight；
The feature vector of four adjacent cell factories is together in series and constitutes the gradient orientation histogram of the block；
All pieces of feature vector is together in series and constitutes the HOG feature of the image.
As further technical solution of the invention are as follows: described to be corrected to form correction chart to the gray level image
Picture；It specifically includes: Gamma being carried out to the gray level image and corrects to form correction image.
It is further: it is described to the gray level image carry out Gamma correct to be formed correction image in correction factor be
0.5。
As further technical solution of the invention are as follows: it is described that the correction image is divided into cell factory, it will be terraced
Degree direction is mapped in a certain range, and the gradient magnitude of pixel is projected as weight；Specifically: by the correction image
It is divided into cell factory, in the range of gradient direction is mapped to 180 degree, the gradient magnitude of pixel is thrown as weight
Shadow.
As further technical solution of the invention are as follows: the window to the target area carries out mobile generation sample
This image；Specifically:
Up and down to target area window, left and right four direction moves different pixels respectively and generates several sample images, and
Acceleration processing is carried out to moving operation using circular matrix.
As further technical solution of the invention are as follows: it is described to train ridge regression classifier using the sample image,
Specifically:
If training sample set, the linear regression function of training sample set is obtained；
Calculate complex conjugate transposed matrix；
Nonlinear mapping function is obtained, the linear separability in new space of the sample after making mapping；
Ridge regression classifier is obtained using ridge regression in new space.
As further technical solution of the invention are as follows: the disconnecting link position to consecutive frame image judges, real
Present condition tracking；Specifically:
It can determine whether that disconnecting link movement is completed when consecutive frame image disconnecting link change in location is less than threshold value, realize status tracking.
The present invention also proposes a kind of real-time disconnecting link status tracking system based on KCF, comprising:
Target area determination unit initializes current frame image and determines target area；
HOG feature extraction unit extracts HOG feature to current frame image；
The window of sample generation unit, moving object region generates sample image；
Ridge regression classifier utilizes sample image training ridge regression classifier；
Fresh target Area generation unit predicts next frame image using ridge regression classifier, generates fresh target region, obtains current
The disconnecting link position of frame image；
Judging unit judges the disconnecting link position of consecutive frame image, realizes status tracking.
Beneficial effects of the present invention:
This system is based on KCF algorithm and carries out target locating to disconnecting link monitor video, obtains the state of disconnecting link in video in real time,
Sample is acquired using circular matrix in algorithm, image, moving different pixels respectively obtains new sample upwards, downwards
This image increases the quantity of training sample, is then based on ridge regression with these samples and goes one object detector of training, judgement
Tracking result is target or background.Algorithm using circular matrix Fourier space diagonalizable property by the operation of matrix
It is converted into dot product, greatly reduces operand, improves arithmetic speed, algorithm is made to meet requirement of real-time.Convenient and efficient,
Greatly reduce the human cost during line data-logging.
Detailed description of the invention
Fig. 1 is the real-time disconnecting link status tracking method flow diagram proposed by the present invention based on KCF；
Fig. 2 is the method flow diagram that HOG feature is extracted to current frame image proposed by the present invention；
Fig. 3 is the real-time disconnecting link status tracking system structure chart proposed by the present invention based on KCF.
Specific embodiment
The embodiment of the invention provides the real-time disconnecting link status tracking method based on KCF, KCF(Kernel
Correlation Filter, core correlation filtering) target locating is carried out to disconnecting link monitor video, video is obtained in real time
The state of middle disconnecting link, convenient and efficient greatly reduce the human cost during line data-logging.
Technical solution general thought provided by the invention is as follows:
Real-time disconnecting link status tracking method based on KCF is acquired sample using circular matrix in algorithm, image to
Above, moving different pixels respectively obtains new sample image downwards, the quantity of training sample is increased, then with these samples
One object detector of training is removed based on ridge regression, judges that tracking result is target or background.Algorithm is existed using circular matrix
The operation of matrix is converted dot product by the property of Fourier space diagonalizable, greatly reduces operand, improves fortune
Speed is calculated, algorithm is made to meet requirement of real-time.
It is the core concept of the application above, in order to make those skilled in the art more fully understand application scheme, under
Face is described in further detail the application in conjunction with attached drawing.It should be understood that the specific spy in the embodiment of the present application and embodiment
Sign is the detailed description to technical scheme, rather than the restriction to technical scheme, the case where not conflicting
Under, the technical characteristic in the embodiment of the present application and embodiment can be combined with each other.
Embodiment one
As shown in Figure 1, being the real-time disconnecting link status tracking method flow diagram proposed by the present invention based on KCF.
Referring to Fig.1, the real-time disconnecting link status tracking method based on KCF, comprising the following steps:
Step 101, current frame image is initialized and determines target area；
Step 102, to current frame image extraction HOG feature, (Histogram of Oriented Gradient, direction gradient are straight
Side's figure)；
Step 103, moving object region window generates sample image；
Step 104, sample image training ridge regression classifier is utilized；
Step 105, next frame image is predicted using ridge regression classifier, generate fresh target region, obtain the knife of current frame image
Gate position repeats step 102 to step 105；
Step 106, the disconnecting link position of consecutive frame image is judged, realizes status tracking.
This system is based on KCF algorithm and carries out target locating to disconnecting link monitor video, obtains disconnecting link in video in real time
State is acquired sample using circular matrix in algorithm, image upwards, move different pixels respectively downwards and obtain newly
Sample image, increase the quantity of training sample, then with these samples be based on ridge regression go training one object detector,
Judge that tracking result is target or background.Algorithm using circular matrix Fourier space diagonalizable property by matrix
Operation is converted into dot product, greatly reduces operand, improves arithmetic speed, and algorithm is made to meet requirement of real-time.It is convenient
Efficiently, the human cost during line data-logging is greatly reduced.
In above-mentioned steps 101, current frame image is initialized and determines target area；Specifically:
Current frame image is initialized using the graphic feature of disconnecting link and determines target area.The graphic feature of disconnecting link includes disconnecting link
Folding angle, linear type image etc. indicate the characteristic image of disconnecting link state, this feature image be stored in advance in systems, as
The judgment basis that disconnecting link target area determines.
It referring to fig. 2, is the method flow diagram that HOG feature is extracted to current frame image proposed by the present invention；
As shown in Fig. 2, extracting HOG feature to current frame image, specifically include:
Step 121, gray processing processing is carried out to image and forms gray level image；
Step 122, gray level image is corrected to form correction image；
Step 123, the horizontal direction of each pixel and the gradient of vertical direction in correction image are calculated, each location of pixels is obtained
Gradient magnitude and direction；
Step 124, high-ranking officers' positive image is divided into cell factory, and gradient direction is mapped in a certain range, by the gradient of pixel
Amplitude is projected as weight；
Step 125, the feature vector of four adjacent cell factories is together in series and constitutes the gradient orientation histogram of the block；
Step 126, all pieces of feature vector is together in series and constitutes the HOG feature of the image.
In above-mentioned steps 122, gray level image is corrected to form correction image；Specifically include: to gray level image into
Row Gamma corrects to form correction image.
Wherein, gray level image is carried out Gamma to correct the correction factor to be formed in correction image being 0.5.
In above-mentioned steps 124, high-ranking officers' positive image is divided into cell factory, and gradient direction is mapped in a certain range,
The gradient magnitude of pixel is projected as weight；Specifically: high-ranking officers' positive image is divided into cell factory, and gradient direction is reflected
It is mapped in the range of 180 degree, the gradient magnitude of pixel is projected as weight.
HOG feature is a kind of for characterizing the descriptor of image Local gradient direction and gradient intensity distribution character, and HOG is special
The extraction of sign is broadly divided into six steps, carries out gray processing processing to image first；Then in order to avoid the influence of illumination is to grayscale image
As carrying out Gamma correction, formula are as follows:
；
Wherein F (x, y) is original-gray image, and G (x, y) is the image after correction, and γ is correction factor, generally takes 0.5；
Next the horizontal direction of each pixel and the gradient of vertical direction are calculated according to formula, and calculate each location of pixels
Gradient magnitude and direction.
Gradient horizontally and vertically of the image at pixel (x, y) are as follows:
；
Gradient magnitude and gradient direction at pixel (x, y) are as follows:
；
Small cell factory (cell) is then divided an image into, in the range of gradient direction is mapped to 180 degree, by pixel
Gradient magnitude is projected as weight；Then the feature vector of four cell in a block (block) is together in series with regard to structure
At the gradient orientation histogram of the block；Finally all pieces of feature vector is together in series and just constitutes the HOG spy of the image
Sign.
In step 103, described to the mobile generation sample image of target area window；Specifically:
Up and down to target area window, left and right four direction moves different pixels respectively and generates several sample images, and
Acceleration processing is carried out to moving operation using circular matrix.
It is at step 104, described to train ridge regression classifier using sample image, specifically:
If training sample set, the linear regression function of training sample set is obtained；
Calculate complex conjugate transposed matrix；
Nonlinear mapping function is obtained, the linear separability in new space of the sample after making mapping；
Ridge regression classifier is obtained using ridge regression in new space.
In the embodiment of the present invention, using sample image training ridge regression classifier, if training sample set, then
Its linear regression function:
；
WhereinIt is weight coefficient, can be solved by least square method:
；
WhereinFor guaranteeing the Generalization Capability of classifier, matrix form are as follows:
；
Wherein,
；
The every a line of X indicates a vector, and y is column vector, and the label of the corresponding sample of each element, then enabling its derivative is 0,
It can acquire:
,
Complex field form is
；
WhereinIndicate complex conjugate transposed matrix.
Since training sample is obtained by target sample cyclic shift,For a circular matrix, all circulations
Matrix can carry out diagonalization using discrete fourier matrix in fourier space, and it is constant that wherein F, which is discrete fourier matrix,；
It will
；
Ridge regression formula is substituted into obtain
；
Because
；
To above formula both sides, Fourier transform is obtained simultaneously
；
Then
；
I.e.。
Actually need to solve in many cases is nonlinear problem, but NONLINEAR CALCULATION is got up complexity height, for letter
Change operation, a nonlinear mapping function need to be looked for, make the linear separability in new space of the sample after mapping, then new
A classifier can be found in space using ridge regression, so the weight at this time obtained
Coefficient is
；
W isA vector in the space of row vector, it is possible to enable
；
Above formula becomes
；
The problem is known as the dual problem of w, enables it about column vectorDerivative is 0,
。
For kernel method, nonlinear mapping function is not known generallyConcrete form, and only portray in nuclear space
Nuclear matrix, enable K indicate the nuclear matrix of nuclear space, then
；
Then
；
。
Next frame image can be predicted, then next frame image be carried out above-mentioned by above-mentioned ridge regression classifier
It determines fresh target region, obtains sample image, to obtain series of frames image, judged by the disconnecting link position to consecutive frame image
Realize status tracking.It wherein can determine whether that disconnecting link movement is completed when consecutive frame image disconnecting link change in location is less than threshold value.
Embodiment two
Based on inventive concept same as the real-time disconnecting link status tracking method in previous embodiment based on KCF, the present invention is also mentioned
For the real-time disconnecting link status tracking system based on KCF.
It is the real-time disconnecting link status tracking system structure chart proposed by the present invention based on KCF referring to Fig. 3.
As shown in figure 3, a kind of real-time disconnecting link status tracking system based on KCF, comprising:
Target area determination unit 201 initializes current frame image and determines target area；
HOG feature extraction unit 202 extracts HOG feature to current frame image；
The window of sample generation unit 203, moving object region generates sample image；
Ridge regression classifier 204 utilizes sample image training ridge regression classifier；
Fresh target Area generation unit 205 predicts next frame image using ridge regression classifier, generates fresh target region, obtains
The disconnecting link position of current frame image；
Judging unit 206 judges the disconnecting link position of consecutive frame image, realizes status tracking.
The various change mode and specific example of the real-time disconnecting link status tracking method based on KCF in embodiment one are same
Suitable for the real-time disconnecting link status tracking system based on KCF of the present embodiment, by aforementioned to the real-time disconnecting link state based on KCF
The detailed description of tracking, those skilled in the art are clear that in the present embodiment the real-time disconnecting link shape based on KCF
The implementation method of state tracking system, so this will not be detailed here in order to illustrate the succinct of book.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The system for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of system, the instruction system realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, institute
The those of ordinary skill in category field can still modify to a specific embodiment of the invention referring to above-described embodiment or
Equivalent replacement, these are applying for this pending hair without departing from any modification of spirit and scope of the invention or equivalent replacement
Within bright claims.
Claims (10)
1. the real-time disconnecting link status tracking method based on KCF, which comprises the following steps:
Step 1 initializes current frame image and determines target area；
Step 2 extracts HOG feature to the current frame image；
The window of step 3, the mobile target area generates sample image；
Step 4 utilizes sample image training ridge regression classifier；
Step 5 predicts next frame image using the ridge regression classifier, generates fresh target region, obtain current frame image
Disconnecting link position repeats step 2 to step 5；
Step 6 judges the disconnecting link position of consecutive frame image, realizes status tracking.
2. the real-time disconnecting link status tracking method according to claim 1 based on KCF, which is characterized in that described to current
Frame image initial determines target area；Specifically:
Current frame image is initialized using the graphic feature of disconnecting link and determines target area.
3. the real-time disconnecting link status tracking method according to claim 1 based on KCF, which is characterized in that described to described
Current frame image extracts HOG feature, specifically includes:
Gray processing processing is carried out to image and forms gray level image；
The gray level image is corrected to form correction image；
The horizontal direction of each pixel and the gradient of vertical direction in the correction image are calculated, the ladder of each location of pixels is obtained
Spend amplitude and direction；
The correction image is divided into cell factory, gradient direction is mapped in a certain range, by the gradient magnitude of pixel
It is projected as weight；
The feature vector of four adjacent cell factories is together in series and constitutes the gradient orientation histogram of the block；
All pieces of feature vector is together in series and constitutes the HOG feature of the image.
4. the real-time disconnecting link status tracking method according to claim 3 based on KCF, which is characterized in that described to described
Gray level image is corrected to form correction image；It specifically includes: Gamma being carried out to the gray level image and corrects to form correction chart
Picture.
5. the real-time disconnecting link status tracking method according to claim 4 based on KCF, which is characterized in that described to described
Gray level image carries out Gamma and corrects the correction factor to be formed in correction image to be 0.5.
6. the real-time disconnecting link status tracking method according to claim 3 based on KCF, which is characterized in that it is described will be described
Correction image be divided into cell factory, gradient direction is mapped in a certain range, using the gradient magnitude of pixel as weight into
Row projection；Specifically: the correction image is divided into cell factory, in the range of gradient direction is mapped to 180 degree, by picture
The gradient magnitude of element is projected as weight.
7. the real-time disconnecting link status tracking method according to claim 3 based on KCF, which is characterized in that described to described
The window of target area carries out mobile generation sample image；Specifically:
Up and down to target area window, left and right four direction moves different pixels respectively and generates several sample images, and
Acceleration processing is carried out to moving operation using circular matrix.
8. the real-time disconnecting link status tracking method according to claim 1 based on KCF, which is characterized in that described to utilize institute
Sample image training ridge regression classifier is stated, specifically:
If training sample set, the linear regression function of training sample set is obtained；
Calculate complex conjugate transposed matrix；
Nonlinear mapping function is obtained, the linear separability in new space of the sample after making mapping；
Ridge regression classifier is obtained using ridge regression in new space.
9. the real-time disconnecting link status tracking method according to claim 1 based on KCF, which is characterized in that described to adjacent
The disconnecting link position of frame image is judged, realizes status tracking；Specifically:
It can determine whether that disconnecting link movement is completed when consecutive frame image disconnecting link change in location is less than threshold value, realize status tracking.
10. any method proposes a kind of real-time disconnecting link status tracking system based on KCF in -9 according to claim 1,
It is characterised by comprising:
Target area determination unit initializes current frame image and determines target area；
HOG feature extraction unit extracts HOG feature to current frame image；
The window of sample generation unit, moving object region generates sample image；
Ridge regression classifier utilizes sample image training ridge regression classifier；
Fresh target Area generation unit predicts next frame image using ridge regression classifier, generates fresh target region, obtains current
The disconnecting link position of frame image；
Judging unit judges the disconnecting link position of consecutive frame image, realizes status tracking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910605666.2A CN110378260B (en) | 2019-07-05 | 2019-07-05 | KCF-based real-time disconnecting link state tracking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910605666.2A CN110378260B (en) | 2019-07-05 | 2019-07-05 | KCF-based real-time disconnecting link state tracking method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378260A true CN110378260A (en) | 2019-10-25 |
| CN110378260B CN110378260B (en) | 2024-02-06 |
Family
ID=68252079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910605666.2A Active CN110378260B (en) | 2019-07-05 | 2019-07-05 | KCF-based real-time disconnecting link state tracking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378260B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814734A (en) * | 2020-07-24 | 2020-10-23 | 南方电网数字电网研究院有限公司 | Method for identifying state of knife switch |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067018A (en) * | 2016-12-09 | 2017-08-18 | 南京理工大学 | A kind of hot line robot bolt recognition methods based on random Hough transformation and SVM |
| CN107341820A (en) * | 2017-07-03 | 2017-11-10 | 郑州轻工业学院 | A kind of fusion Cuckoo search and KCF mutation movement method for tracking target |
| CN108665487A (en) * | 2017-10-17 | 2018-10-16 | 国网河南省电力公司郑州供电公司 | Substation's manipulating object and object localization method based on the fusion of infrared and visible light |
| CN109741369A (en) * | 2019-01-03 | 2019-05-10 | 北京邮电大学 | A kind of method and system for robotic tracking target pedestrian |
| WO2019129255A1 (en) * | 2017-12-29 | 2019-07-04 | 华为技术有限公司 | Target tracking method and device |
-
2019
- 2019-07-05 CN CN201910605666.2A patent/CN110378260B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107067018A (en) * | 2016-12-09 | 2017-08-18 | 南京理工大学 | A kind of hot line robot bolt recognition methods based on random Hough transformation and SVM |
| CN107341820A (en) * | 2017-07-03 | 2017-11-10 | 郑州轻工业学院 | A kind of fusion Cuckoo search and KCF mutation movement method for tracking target |
| CN108665487A (en) * | 2017-10-17 | 2018-10-16 | 国网河南省电力公司郑州供电公司 | Substation's manipulating object and object localization method based on the fusion of infrared and visible light |
| WO2019129255A1 (en) * | 2017-12-29 | 2019-07-04 | 华为技术有限公司 | Target tracking method and device |
| CN109741369A (en) * | 2019-01-03 | 2019-05-10 | 北京邮电大学 | A kind of method and system for robotic tracking target pedestrian |
Non-Patent Citations (1)
| Title |
|---|
| 梅立雪;汪兆栋;张浦哲;: "一种邻帧匹配与卡尔曼滤波相结合的多目标跟踪算法" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814734A (en) * | 2020-07-24 | 2020-10-23 | 南方电网数字电网研究院有限公司 | Method for identifying state of knife switch |
| CN111814734B (en) * | 2020-07-24 | 2024-01-26 | 南方电网数字电网研究院有限公司 | Method for identifying state of disconnecting link |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378260B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539273B (en) | Traffic video background modeling method and system | |
| CN106650630B (en) | A kind of method for tracking target and electronic equipment | |
| CN110807496B (en) | Dense target detection method | |
| CN108197623A (en) | For detecting the method and apparatus of target | |
| CN105809716B (en) | Foreground extraction method integrating superpixel and three-dimensional self-organizing background subtraction method | |
| CN108229524A (en) | A kind of chimney and condensing tower detection method based on remote sensing images | |
| CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
| CN102073846A (en) | Method for acquiring traffic information based on aerial images | |
| CN109766828A (en) | A kind of vehicle target dividing method, device and communication equipment | |
| CN111062331B (en) | Image mosaic detection method and device, electronic equipment and storage medium | |
| CN110176024A (en) | Method, apparatus, equipment and the storage medium that target is detected in video | |
| CN109752855A (en) | A kind of method of hot spot emitter and detection geometry hot spot | |
| CN104346817B (en) | A kind of video image color cast detection method and device | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN110164341A (en) | Circuit device, electronic equipment and error-detecting method | |
| CN112633313B (en) | Bad information identification method of network terminal and local area network terminal equipment | |
| CN106327525A (en) | Machine room important place border-crossing behavior real-time monitoring method | |
| CN109840905A (en) | Power equipment rusty stain detection method and system | |
| CN110378260A (en) | Real-time disconnecting link status tracking method and system based on KCF | |
| CN101561316B (en) | On-line test visual data processing system based on region of interest (ROI) | |
| CN106780544B (en) | The method and apparatus that display foreground extracts | |
| CN106650824B (en) | Moving object classification method based on support vector machines | |
| CN110689001B (en) | Method for generating license plate training sample in complex environment | |
| CN112017148A (en) | Method and device for extracting single-joint skeleton contour | |
| CN109753958A (en) | Image character recognition methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |